PhilSad's picture
First Push
e605b57
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.4077636003494263,
"min": 1.4077636003494263,
"max": 2.8713154792785645,
"count": 12
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13410.3564453125,
"min": 13410.3564453125,
"max": 29405.142578125,
"count": 12
},
"SnowballTarget.Step.mean": {
"value": 119952.0,
"min": 9952.0,
"max": 119952.0,
"count": 12
},
"SnowballTarget.Step.sum": {
"value": 119952.0,
"min": 9952.0,
"max": 119952.0,
"count": 12
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 10.457113265991211,
"min": 0.541290819644928,
"max": 10.457113265991211,
"count": 12
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2039.1370849609375,
"min": 105.01041412353516,
"max": 2081.87744140625,
"count": 12
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 12
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 12
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06810767521714226,
"min": 0.06445879150511853,
"max": 0.07636864510805383,
"count": 12
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.272430700868569,
"min": 0.2610952785813852,
"max": 0.3818432255402691,
"count": 12
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22517453513893426,
"min": 0.13410573917459334,
"max": 0.2876457434074552,
"count": 12
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.900698140555737,
"min": 0.5364229566983734,
"max": 1.4382287170372758,
"count": 12
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.000126882057706,
"min": 0.000126882057706,
"max": 0.000291882002706,
"count": 12
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.000507528230824,
"min": 0.000507528230824,
"max": 0.00138516003828,
"count": 12
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.142294,
"min": 0.142294,
"max": 0.19729400000000002,
"count": 12
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.569176,
"min": 0.569176,
"max": 0.96172,
"count": 12
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0021204706000000004,
"min": 0.0021204706000000004,
"max": 0.0048649706,
"count": 12
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.008481882400000001,
"min": 0.008481882400000001,
"max": 0.023089828,
"count": 12
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 21.555555555555557,
"min": 3.75,
"max": 22.09259259259259,
"count": 12
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 970.0,
"min": 165.0,
"max": 1193.0,
"count": 12
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 21.555555555555557,
"min": 3.75,
"max": 22.09259259259259,
"count": 12
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 970.0,
"min": 165.0,
"max": 1193.0,
"count": 12
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684276312",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1684276657"
},
"total": 345.298323523,
"count": 1,
"self": 0.14640488999998524,
"children": {
"run_training.setup": {
"total": 0.0422419889999901,
"count": 1,
"self": 0.0422419889999901
},
"TrainerController.start_learning": {
"total": 345.10967664400005,
"count": 1,
"self": 0.5216589780018239,
"children": {
"TrainerController._reset_env": {
"total": 4.33700786199995,
"count": 1,
"self": 4.33700786199995
},
"TrainerController.advance": {
"total": 339.9846970079983,
"count": 11732,
"self": 0.218629206988453,
"children": {
"env_step": {
"total": 339.76606780100985,
"count": 11732,
"self": 248.08728065200717,
"children": {
"SubprocessEnvManager._take_step": {
"total": 91.45360304100643,
"count": 11732,
"self": 1.3051969109947095,
"children": {
"TorchPolicy.evaluate": {
"total": 90.14840613001172,
"count": 11732,
"self": 90.14840613001172
}
}
},
"workers": {
"total": 0.225184107996256,
"count": 11731,
"self": 0.0,
"children": {
"worker_root": {
"total": 343.4920205520008,
"count": 11731,
"is_parallel": true,
"self": 159.90358903399897,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006310437999900387,
"count": 1,
"is_parallel": true,
"self": 0.004734273999929428,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015761639999709587,
"count": 10,
"is_parallel": true,
"self": 0.0015761639999709587
}
}
},
"UnityEnvironment.step": {
"total": 0.11071557899992968,
"count": 1,
"is_parallel": true,
"self": 0.0006850269999176817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004963410000300428,
"count": 1,
"is_parallel": true,
"self": 0.0004963410000300428
},
"communicator.exchange": {
"total": 0.10717107099992518,
"count": 1,
"is_parallel": true,
"self": 0.10717107099992518
},
"steps_from_proto": {
"total": 0.0023631400000567737,
"count": 1,
"is_parallel": true,
"self": 0.00041232899991427985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019508110001424939,
"count": 10,
"is_parallel": true,
"self": 0.0019508110001424939
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 183.5884315180018,
"count": 11730,
"is_parallel": true,
"self": 7.063917442989805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.007958655009247,
"count": 11730,
"is_parallel": true,
"self": 4.007958655009247
},
"communicator.exchange": {
"total": 146.9205599660088,
"count": 11730,
"is_parallel": true,
"self": 146.9205599660088
},
"steps_from_proto": {
"total": 25.595995453993964,
"count": 11730,
"is_parallel": true,
"self": 5.212864104964069,
"children": {
"_process_rank_one_or_two_observation": {
"total": 20.383131349029895,
"count": 117300,
"is_parallel": true,
"self": 20.383131349029895
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00022242799991545326,
"count": 1,
"self": 0.00022242799991545326,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 337.28294733989856,
"count": 330039,
"is_parallel": true,
"self": 7.663260997965153,
"children": {
"process_trajectory": {
"total": 187.18189858693336,
"count": 330039,
"is_parallel": true,
"self": 186.71473594993336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.46716263700000127,
"count": 2,
"is_parallel": true,
"self": 0.46716263700000127
}
}
},
"_update_policy": {
"total": 142.43778775500004,
"count": 58,
"is_parallel": true,
"self": 52.77930697800002,
"children": {
"TorchPPOOptimizer.update": {
"total": 89.65848077700002,
"count": 2955,
"is_parallel": true,
"self": 89.65848077700002
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.26609036800005015,
"count": 1,
"self": 0.0013557920001403545,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2647345759999098,
"count": 1,
"self": 0.2647345759999098
}
}
}
}
}
}
}